Various embodiments of the present application set forth a computer-implemented method that includes processing a first natural language (NL) request, where the first NL request includes a first artifact. The method further includes determining that a first relationship, associated with the first artifact and useable to process the first NL request, is unavailable in a first NL language processing system. The method further includes generating a first data relationship recommendation based on the first NL request. In addition, the method includes causing the first data relationship recommendation to be provided to a user.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A computer-implemented method, comprising: processing a first natural language (NL) request, wherein the first NL request includes a first artifact; determining that a first data relationship, associated with the first artifact and useable to process the first NL request, is unavailable in a first NL language processing system; generating a first data relationship recommendation based on the first NL request, wherein the first data relationship recommendation includes a first element, a second element, and an action that specifies how the first element and the second element are to be linked; and causing the first data relationship recommendation to be provided to a user.
2. The computer-implemented method of claim 1 , further comprising: generating a first data model recommendation by: determining that a first data model associated with the first data relationship is unavailable in the first NL processing system; identifying, based on the first artifact, a plurality of candidate data models included in a first data storage system associated with a first domain-specific language (DSL) language processing system; and selecting a first candidate data model from the plurality of candidate data models.
3. The computer-implemented method of claim 1 , wherein the first artifact comprises one of a data model, an entity, a named entity, an attribute, a fixed value, a synonym, or a context.
4. The computer-implemented method of claim 1 , wherein generating the first data relationship recommendation comprises: extracting, from the first NL request, a first set of artifacts including the first artifact; for each artifact in the first set of artifacts, identifying a corresponding artifact stored in the first NL language processing system to generate a first set of corresponding artifacts; combining two or more corresponding artifacts of the first set of corresponding artifacts to generate a first candidate relationship; and including the first candidate relationship in the first data relationship recommendation.
5. The computer-implemented method of claim 1 , further comprising: determining that the user selected the first data relationship recommendation, wherein the first data relationship recommendation includes a first candidate relationship; and storing the first candidate relationship in the first NL language processing system.
6. The computer-implemented method of claim 1 , further comprising: storing, in the first NL language processing system, a first relationship included in the first data relationship recommendation; mapping the first relationship to an intent associated with the first NL request; extracting a first set of artifacts from the intent; and generating a first training data set based on the first set of artifacts.
7. The computer-implemented method of claim 1 , further comprising: storing, in the first NL language processing system, a first relationship included in the first data relationship recommendation; identifying a first set of artifacts based on the first relationship; and generating a first training data set based on the first set of artifacts, wherein the first training data set comprises a JavaScript Object Notation (JSON) file storing first set of artifacts and the first DSL relationship.
8. The computer-implemented method of claim 1 , further comprising: storing, in the first NL language processing system, a first relationship included in the first data relationship recommendation; identifying a first set of artifacts based on the first relationship; and generating a first training data set based on the first set of artifacts, wherein the first training data set includes a user intent associated with the first relationship.
9. The computer-implemented method of claim 1 , further comprising: storing, in the first NL language processing system, a first relationship included in the first data relationship recommendation; identifying a first set of artifacts based on the first relationship; and generating a first training data set based on the first set of artifacts by: selecting a first NL template associated with the first NL processing system, the first NL template including a first set of fields; for each field included in the first set of fields, extracting, from the first relationship, a corresponding artifact to generate a second set of artifacts; generating the first training data set based on a second set of the artifacts and the first DSL template; and publishing the first training data set.
10. The computer-implemented method of claim 1 , further comprising: storing, in the first NL language processing system, a first relationship included in the first data relationship recommendation; identifying a first set of artifacts based on the first relationship; and generating a first training data set based on the first set of artifacts by: selecting a first NL template associated with the first NL processing system, wherein the first NL template is one of: an Alexa skill template, a Google Dialog template, a first artificial intelligence modeling language (AIML) template, or a first Artificial Intelligence: RiveScript (AiRS) template, and wherein the first NL template including a first set of fields; for each field included in the first set of fields, extracting, from the first relationship, a corresponding artifact to generate a second set of artifacts; generating the first training data set based on a second set of the artifacts and the first DSL template; and publishing the first training data set.
11. One or more non-transitory computer-readable storage media including instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of: processing a first natural language (NL) request, wherein the first NL request includes a first artifact; determining that a first data relationship, associated with the first artifact and useable to process the first NL request, is unavailable in a first NL language processing system; generating a first data relationship recommendation based on the first NL request, wherein the first data relationship recommendation includes a first element, a second element, and an action that specifies how the first element and the second element are to be linked; and causing the first data relationship recommendation to be provided to a user.
12. The one or more non-transitory computer-readable storage media of claim 11 , wherein the processor further performs the steps of: generating a first data model recommendation by: determining that a first data model associated with the first data relationship is unavailable in the first NL processing system; identifying, based on the first artifact, a plurality of candidate data models included in a first data storage system associated with a first domain-specific language (DSL) language processing system; and selecting a first candidate data model from the plurality of candidate data models.
13. The one or more non-transitory computer-readable storage media of claim 11 , wherein the first artifact comprises one of a data model, an entity, a named entity, an attribute, a fixed value, a synonym, or a context.
14. The one or more non-transitory computer-readable storage media of claim 11 , wherein the instructions for generating the first data relationship recommendation comprise: extracting, from the first NL request, a first set of artifacts including the first artifact; for each artifact in the first set of artifacts, identifying a corresponding artifact stored in the first NL language processing system to generate a first set of corresponding artifacts; combining two or more corresponding artifacts of the first set of corresponding artifacts to generate a first candidate relationship; and including the first candidate relationship in the first data relationship recommendation.
15. The one or more non-transitory computer-readable storage media of claim 11 , wherein the processor further performs the steps of: determining that the user selected the first data relationship recommendation, wherein the first data relationship recommendation includes a first candidate relationship; and storing the first candidate relationship in the first NL language processing system.
16. The one or more non-transitory computer-readable storage media of claim 11 , wherein the processor further performs the steps of: storing, in the first NL language processing system, a first relationship included in the first data relationship recommendation; mapping the first relationship to an intent associated with the first NL request; extracting a first set of artifacts from the intent; and generating a first training data set based on the first set of artifacts.
17. The one or more non-transitory computer-readable storage media of claim 11 , wherein the processor further performs the steps of: storing, in the first NL language processing system, a first relationship included in the first data relationship recommendation; identifying a first set of artifacts based on the first relationship; and generating a first training data set based on the first set of artifacts, wherein the first training data set comprises a JavaScript Object Notation (JSON) file storing first set of artifacts and the first DSL relationship.
18. The one or more non-transitory computer-readable storage media of claim 11 , wherein the processor further performs the steps of: storing, in the first NL language processing system, a first relationship included in the first data relationship recommendation; identifying a first set of artifacts based on the first relationship; and generating a first training data set based on the first set of artifacts, wherein the first training data set includes a user intent associated with the first relationship.
19. The one or more non-transitory computer-readable storage media of claim 11 , wherein the processor further performs the steps of: storing, in the first NL language processing system, a first relationship included in the first data relationship recommendation; identifying a first set of artifacts based on the first relationship; and generating a first training data set based on the first set of artifacts by: selecting a first NL template associated with the first NL processing system, the first NL template including a first set of fields; for each field included in the first set of fields, extracting, from the first relationship, a corresponding artifact to generate a second set of artifacts; generating the first training data set based on a second set of the artifacts and the first DSL template; and publishing the first training data set.
20. The one or more non-transitory computer-readable storage media of claim 11 , wherein the processor further performs the steps of: storing, in the first NL language processing system, a first relationship included in the first data relationship recommendation; identifying a first set of artifacts based on the first relationship; and generating a first training data set based on the first set of artifacts by: selecting a first NL template associated with the first NL processing system, wherein the first NL template is one of: an Alexa skill template, a Google Dialog template, a first artificial intelligence modeling language (AIML) template, or a first Artificial Intelligence: RiveScript (AiRS) template, and wherein the first NL template including a first set of fields; for each field included in the first set of fields, extracting, from the first relationship, a corresponding artifact to generate a second set of artifacts; generating the first training data set based on a second set of the artifacts and the first DSL template; and publishing the first training data set.
21. A computing device, comprising: a memory that includes an application; and a processor that is coupled to the memory, and when executing the application, performs: processing a first natural language (NL) request, wherein the first NL request includes a first artifact; determining that a first data relationship, associated with the first artifact and useable to process the first NL request, is unavailable in a first NL language processing system; generating a first data relationship recommendation based on the first NL request, wherein the first data relationship recommendation includes a first element, a second element, and an action that specifies how the first element and the second element are to be linked; and causing the first data relationship recommendation to be provided to a user.
22. The computing device of claim 21 , wherein the processor further performs: generating a first data model recommendation by: determining that a first data model associated with the first data relationship is unavailable in the first NL processing system; identifying, based on the first artifact, a plurality of candidate data models included in a first data storage system associated with a first domain-specific language (DSL) language processing system; and selecting a first candidate data model from the plurality of candidate data models.
23. The computing device of claim 21 , wherein the first artifact comprises one of a data model, an entity, a named entity, an attribute, a fixed value, a synonym, or a context.
24. The computing device of claim 21 , wherein generating the first data relationship recommendation comprises: extracting, from the first NL request, a first set of artifacts including the first artifact; for each artifact in the first set of artifacts, identifying a corresponding artifact stored in the first NL language processing system to generate a first set of corresponding artifacts; combining two or more corresponding artifacts of the first set of corresponding artifacts to generate a first candidate relationship; and including the first candidate relationship in the first data relationship recommendation.
25. The computing device of claim 21 , wherein the processor further performs: determining that the user selected the first data relationship recommendation, wherein the first data relationship recommendation includes a first candidate relationship; and storing the first candidate relationship in the first NL language processing system.
26. The computing device of claim 21 , wherein the processor further performs: storing, in the first NL language processing system, a first relationship included in the first data relationship recommendation; mapping the first relationship to an intent associated with the first NL request; extracting a first set of artifacts from the intent; and generating a first training data set based on the first set of artifacts.
27. The computing device of claim 21 , wherein the processor further performs: storing, in the first NL language processing system, a first relationship included in the first data relationship recommendation; identifying a first set of artifacts based on the first relationship; and generating a first training data set based on the first set of artifacts, wherein the first training data set comprises a JavaScript Object Notation (JSON) file storing first set of artifacts and the first DSL relationship.
28. The computing device of claim 21 , wherein the processor further performs: storing, in the first NL language processing system, a first relationship included in the first data relationship recommendation; identifying a first set of artifacts based on the first relationship; and generating a first training data set based on the first set of artifacts, wherein the first training data set includes a user intent associated with the first relationship.
29. The computing device of claim 21 , wherein the processor further performs: storing, in the first NL language processing system, a first relationship included in the first data relationship recommendation; identifying a first set of artifacts based on the first relationship; and generating a first training data set based on the first set of artifacts by: selecting a first NL template associated with the first NL processing system, the first NL template including a first set of fields; for each field included in the first set of fields, extracting, from the first relationship, a corresponding artifact to generate a second set of artifacts; generating the first training data set based on a second set of the artifacts and the first DSL template; and publishing the first training data set.
30. The computing device of claim 21 , wherein the processor further performs: storing, in the first NL language processing system, a first relationship included in the first data relationship recommendation; identifying a first set of artifacts based on the first relationship; and generating a first training data set based on the first set of artifacts by: selecting a first NL template associated with the first NL processing system, wherein the first NL template is one of: an Alexa skill template, a Google Dialog template, a first artificial intelligence modeling language (AIML) template, or a first Artificial Intelligence: RiveScript (AiRS) template, and wherein the first NL template including a first set of fields; for each field included in the first set of fields, extracting, from the first relationship, a corresponding artifact to generate a second set of artifacts; generating the first training data set based on a second set of the artifacts and the first DSL template; and publishing the first training data set.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
September 28, 2018
February 16, 2021
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.